buzz_remove_member

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly flags the operation as 'Destructive' and explains the permission requirement tied to the caller's role. It also clarifies the identity formats for 'user'. This is significant, actionable context beyond the definition of the operation itself.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no wasted words. The core action and NIP reference are front-loaded, followed immediately by the destructive nature and user-format guidance. Every phrase earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the key aspects an agent needs: the action, the destructive nature, the role prerequisite, and identity formats. Given there is no output schema, the lack of a return-value note is acceptable. The only notable gap is the ambiguous 'channel' parameter, which, if clarified (e.g., pointing to a channel ID from buzz_channels), would make it complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%: the 'user' parameter already has a description in the schema, and the tool description merely repeats those formats ('npub / hex pubkey / exact display-name / email') without adding new meaning. The 'channel' parameter has no schema description, but the description also fails to explain what a channel identifier is (e.g., channel ID, name, or NIP-29 reference). It does not compensate for the undocumented parameter, while also adding nothing new for the documented one.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ('Remove'), a resource ('a person from a channel'), and adds useful context with 'NIP-29 kind 9001' and 'as you'. This clearly distinguishes it from siblings like buzz_add_member (opposite action) and buzz_channel_members (viewing). The purpose is unmistakable even without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear context on when the tool can be used by stating 'the relay only allows it where your OWN role permits (owner/admin)'. However, it does not explicitly name the alternative (e.g., 'for adding a member, use buzz_add_member') or clarify when another tool would be more appropriate, so it falls just short of the strongest usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.